1. Project Overview and Objectives¶
The goal of this project is to carry out a thorough comparison between three distinct transfer learning models - VGG16, InceptionV3, and ResNet50 and accuracy has been used as a metric to measure the models performance
$\textrm{Accuracy} = \frac{\textrm{Number of correclty predicted images}}{\textrm{Total number of tested images}} \times 100\%$
Final results look as follows:
| Set | Accuracy |
|---|---|
| Validation Set* | ~92% |
| Test Set* | ~92% |
*
validation set- is the set used during the model training to adjust the hyperparameters.test set- is the set which is used to evaluate model's performance
2. Data Set Description¶
The image data that was used for this problem is Brain MRI Images for Brain Tumor Detection. It conists of MRI scans of two classes:
NO- no tumor, encoded as0YES- tumor, encoded as1
Unfortunately, the data set description doesn't hold any information where this MRI scans come from..
3. What is Brain Tumor?¶
A brain tumor occurs when abnormal cells form within the brain. There are two main types of tumors: cancerous (malignant) tumors and benign tumors. Cancerous tumors can be divided into primary tumors, which start within the brain, and secondary tumors, which have spread from elsewhere, known as brain metastasis tumors. All types of brain tumors may produce symptoms that vary depending on the part of the brain involved. These symptoms may include headaches, seizures, problems with vision, vomiting and mental changes. The headache is classically worse in the morning and goes away with vomiting. Other symptoms may include difficulty walking, speaking or with sensations. As the disease progresses, unconsciousness may occur.
Brain metastasis in the right cerebral hemisphere from lung cancer, shown on magnetic resonance imaging.
Source: Wikipedia
